© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13541
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation in lists or series of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.76
    writeFieldEnd
    -0.68
    رشف
    -0.66
     Merv
    -0.65
    webElement
    -0.65
     something
    -0.62
    ddots
    -0.61
     HasFactory
    -0.61
    RenderAtEndOf
    -0.61
     somewhere
    -0.59
    POSITIVE LOGITS
     Saltar
    0.58
     Bühne
    0.58
    檚
    0.55
     Jr
    0.54
    ⓘ
    0.51
     collaborator
    0.50
    iyor
    0.49
    *,
    0.48
     οποίο
    0.47
     countrymen
    0.47
    Activations Density 0.120%

    No Known Activations